Application of systems of orthogonal functions for formation of sign space in image classification methods
Article Sidebar
Main Article Content
Abstract
The subject of the article's research is the improvement of structural methods of image classification in computer vision systems. The goal is to reduce computational costs for classification by implementing a device for decomposing image description components using a system of orthogonal functions and implementing feature space compression models. Applied methods: ORB key point detector, set theory apparatus and vector spaces, metric models for determining relevance to sets of multidimensional vectors, theory of orthogonal decomposition of vectors, elements of probability theory, software modeling. Obtained results: modifications of the image classification method based on the introduction of orthogonal data decomposition in vector space were developed, models were proposed for data compression in the transformed feature space, Tanimoto metric was introduced for image comparison, a threshold selection method was established for determining equivalent description components. The effectiveness of the developed modifications of the classifier depends on the selection of a subset of functions for decomposition, the metric for comparing descriptions, and the method of determining the equivalence threshold. The implementation of the apparatus of orthogonal functions not only reduced computational costs tenfold, but also ensured sufficiently high indicators of classification performance and interference resistance. The practical significance of the work is the construction of new models of the image classifier in the transformed space of features, confirmation of the functionality, speed and immunity of the proposed modifications on examples of images, the creation of a software application for the implementation of the developed classification methods in computer vision systems.
Article Details
References
Ahmed, N. and Rao, K.R. (1975), Orthogonal Transforms for Digital Signal Processing, Springer Ferlag Berlin, 248 p.
Scherer, R. (2020), “Computer Vision Methods for Fast Image Classification and Retrieval”, Studies in Computation Intelligence 821, Springer Nature Switzerland AG 2020, doi: https://doi.org/10.1007/978-3-030-12195-2.
Pratt W. K. (2001), Digital Image Processing, New York: John Wiley and Sons Inc., 723 p.
Vlasenko, N.V. and Sytnik, O.V. (2013), “Classification of video-objects in attribute space of the Walsh functions”, Telecommunications and Radio Engineering, Vol. 72(19), pp. 1777-1785.
Flach, P. (2012), Machine Learning. The Art and Science of Algorithms that Make Sense of Data, Cambridge Univer-sity Press: New York, NY, USA, 409 p.
Alessio, S.M. (2016), Digital Signal Processing and Spectral Analysis for Scientists, Springer, 200 p.
Gorokhovatskiy, V.A. (2011), “Compression of Descriptions in the Structural Image Recognition”, Telecommunica-tions and Radio Engineering, Vol. 70, No 15, pp. 1363-1371.
Gorokhovatsky, A.V., Gorokhovatsky, V.A., Vlasenko, A.N. and Vlasenko, N.V. (2014), “Quality Criteria for Multi-dimensional Object Recognition Based Upon Distance Matrices”, Telecommunications and Radio Engineering, Vol. 73, No 18, рр. 1661-1670.
Gorokhovatsky, V.O. and Gadetska, S.V. (2019), “Determination of Relevance of Visual Object Images by Applica-tion of Statistical Analysis of Regarding Fragment Representation of their Descriptions”, Telecommunications and Radio Engineering, Vol. 78 (3), pp. 211-220.
Gorokhovatskyi, V., Gadetska, S. and Ponomarenko, R. (2020), “Recognition of Visual Objects Based on Statistical Distributions for Blocks of Structural Description of Image”, Lecture Notes in Computational Intelligence and Deci-sion Making, Proceedings of the XV International Scientific Conference “Intellectual Systems of Decision Making and Problems of Computational Intelligence” (ISDMCI'2019), Ukraine, May 21–25, 2019, pp. 501-512.
Shapiro, L. (2001), Computer vision, Prentice Hall, 625 p.
Svyrydov, A., Kuchuk, H. and Tsiapa, O. (2018), “Improving efficiently of image recognition process: Approach and case study”, Proceedings of 2018 IEEE 9th International Conference on Dependable Systems, Services and Technol-ogies, DESSERT 2018, pp. 593-597, doi: https://doi.org/10.1109/DESSERT.2018.8409201.
Gorokhovatskyi, V. and Vlasenko, N. (2021), “the image description reduction in the set of descriptors on informa-tiveness metric criteria base”, Advanced Information Systems, Vol. 5, No. 4, pp. 10-16, doi: https://doi.org/10.20998/2522-9052.2021.4.02.14.
Kolmogorov, A.N. and Fomin, S.V. (1976), Elements of the theory of functions and functional analysis, Nauka, Mos-cow, 544 p.
Gorokhovatskyi, V.O. and Tvoroshenko, I.S. (2022), “Analysis of multidimensional data by description in the form of a set of components”, monograph, Khnure, Kharkiv, 124 p., doi: https://doi.org/10.30837/978-966-659-379-8.
Gorokhovatskyi, V.A. (2003), Recognition of images in the conditions of incomplete information, KHNURE, Kharkiv, 112 p.
(2022), ORB feature detector and binary descriptor, available at:
https://scikit-image.org/docs/dev/auto_examples/features_detection/plot_orb.
Rublee, E., Rabaud, V., Konolige, K., and Bradski, G. (2011), “ORB: an efficient alternative to SIFT or SURF”, Pro-ceedings IEEE International Conferenceon Computer Vision (ICCV), pp. 2564-2571.
Manning, C.D., Raghavan, P. and Schutze, H. (2008), Introduction to Information Retrieval, University Press, Cam-bridge, 528 p.
Gorokhovatsky, V.A. and Putyatin, Y. P. (2009), “Image Likelihood Measures of the Basis of the Set of Conformities”, Telecommunications and Radio Engineering, Vol. 68 (9), pp. 763–778.
Zalmanzon, L.A. (1989), Fourier, Walsh, Haar transforms and their application in control, communications and other areas, Nauka, Moscow, 496 p.
Eresko, Y.N. (2002), Localization of images in automatic viewfinders, Sputnik+ Company, Moscow, 357 p.
Yakovleva, O., and Nikolaieva, K. (2020), “Research of descriptor-based image normalization and comparative analy-sis of SURF, SIFT, BRISK, ORB, KAZE, AKAZE descriptors”, Advanced Information Systems, Vol. 4, No.4, pp. 89-101, doi: https://doi.org/10.20998/2522-9052.2020.4.13.
Nong, Ye. (2013), Data Mining: Theories, Algorithms, and Examples, CRC Press, Florida, USA, 349 p.
Daradkeh, Y.I., Gorokhovatskyi, V., Tvoroshenko, I., Gadetska, S., and Al-Dhaifallah, M. (2021), “Methods of Classi-fication of Images in the Basis of the Values of Statistical Distributions for the Composition of Structural Description Components”, IEEE Access, Vol. 9, pp. 929.64-929.73, doi: https://doi.org/10.1109/ACCESS.2021.3093457.
Daradkeh, Y.I., Gorokhovatskyi, V., Tvoroshenko, I. and Al-Dhaifallah, M. (2022), “Classification of Images Based on a System of Hierarchical Features”, Computers, Materials & Continua, Vol. 72(1), pp. 1785-1797, doi:
https://doi.org/10.32604/cmc.2022.025499.
Gorokhovatskyi, V.O., Gadetska, S.V. and Stiahlyk, N.I. (2019), “Exploring the Statistical Properties of a Block Rep-resentation Model for a Set of Image Keypoint Descriptors”, Radio Electronics, Computer Science, Control, No. 2, pp. 100-107.
Gadetska, S., Gorokhovatskyi, V., Stiahlyk, N. and Vlasenko, N. (2022), “Aggregate Parametric Representation of Image Structural Description in Statistical Classification Methods”, CEUR Workshop Proceedings: Computer Model-ing and Intelligent Systems (CMIS-2022), 3137, pp. 68-77, doi: https://doi.org/10.32782/cmis/3137-6.